Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.1700

Data Index: 2884958 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3689. Min Act: -0.1700

Data Index: 1475294 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3383. Min Act: -0.1700

Data Index: 7562932 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3515. Min Act: -0.1700

Data Index: 4632709 (Open Web Text)

Max Activating Token Index: 499

Text #4

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3370. Min Act: -0.1700

Data Index: 1592429 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3229. Min Act: -0.1700

Data Index: 1289267 (Open Web Text)

Max Activating Token Index: 596

Text #6

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3225. Min Act: -0.1700

Data Index: 7151605 (Open Web Text)

Max Activating Token Index: 470

Text #7

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3431. Min Act: -0.1700

Data Index: 4711731 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3343. Min Act: -0.1700

Data Index: 1613864 (Open Web Text)

Max Activating Token Index: 440

Text #9

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3259. Min Act: -0.1700

Data Index: 4238517 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3343. Min Act: -0.1700

Data Index: 1125794 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3283. Min Act: -0.1700

Data Index: 3376158 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3249. Min Act: -0.1700

Data Index: 1125186 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3379. Min Act: -0.1700

Data Index: 3020443 (Open Web Text)

Max Activating Token Index: 305

Text #14

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3155. Min Act: -0.1700

Data Index: 2262474 (Open Web Text)

Max Activating Token Index: 410

Text #15

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3215. Min Act: -0.1700

Data Index: 2357847 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3056. Min Act: -0.1700

Data Index: 7722901 (Open Web Text)

Max Activating Token Index: 810

Text #17

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3139. Min Act: -0.1700

Data Index: 4191555 (Open Web Text)

Max Activating Token Index: 922

Text #18

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3191. Min Act: -0.1700

Data Index: 2447487 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3320. Min Act: -0.1700

Data Index: 4389566 (Open Web Text)

Max Activating Token Index: 1014